5 papers
AstroReason-Bench: Evaluating Unified Agentic Planning across Heterogeneous Space Planning Problems
Weiyi Wang, Xinchi Chen, Jingjing Gong +2
Recent advances in agentic Large Language Models (LLMs) have positioned them as generalist planners capable of reasoning and acting across diverse tasks. However, existing agent be…
EmbeddingGemma: Powerful and Lightweight Text Representations
Henrique Schechter Vera, Sahil Dua, Biao Zhang +86
We introduce EmbeddingGemma, a new lightweight, open text embedding model based on the Gemma 3 language model family. Our innovative training recipe strategically captures knowledg…
Interleaved Learning and Exploration: A Self-Adaptive Fuzz Testing Framework for MLIR
Zeyu Sun, Jingjing Liang, Weiyi Wang +3
MLIR (Multi-Level Intermediate Representation) has rapidly become a foundational technology for modern compiler frameworks, enabling extensibility across diverse domains. However,…
Boosting Zero-Shot VLN via Abstract Obstacle Map-Based Waypoint Prediction with TopoGraph-and-VisitInfo-Aware Prompting
Boqi Li, Siyuan Li, Weiyi Wang +3
With the rapid progress of foundation models and robotics, vision-language navigation (VLN) has emerged as a key task for embodied agents with broad practical applications. We addr…
Taming Hyperparameter Sensitivity in Data Attribution: Practical Selection Without Costly Retraining
Weiyi Wang, Junwei Deng, Yuzheng Hu +5
Data attribution methods, which quantify the influence of individual training data points on a machine learning model, have gained increasing popularity in data-centric application…